ship-digest

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and analyzes public GitHub content (e.g., "gh api /repos/$GITHUB_USERNAME/{repo}/readme" and commits in "Step 2: Analyze Repo Content" and "Step 1: Fetch New Repos"), which is untrusted, user-generated third-party content that the agent reads and uses to generate drafts, enabling indirect prompt-injection risks.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill calls GitHub API endpoints at runtime (e.g., gh api /repos/$GITHUB_USERNAME/{repo}/readme and gh api /repos/$GITHUB_USERNAME/{repo}/commits) to fetch README and commit data which are injected into the digest-generation flow and therefore directly control the agent's generated prompts/content.